ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-15 03:30:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

gfx942 return

Browse Source
This commit is contained in:
root
2025-09-23 06:55:57 +00:00
parent c2e0f0a0b7
commit 8d978054ff
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck_tile/ops/moe_flatmm/kernel/moe_flatmm_kernel.hpp
View File

@@ -753,6 +753,7 @@ struct MoeFlatmmKernel
template <class MoeFlatmmKernelArgs>
CK_TILE_DEVICE void operator()(MoeFlatmmKernelArgs kargs) const
{
#if defined(__gfx950__)
int partition_idx = blockIdx.x;
int total_work_tile_cnt = TilePartitioner::GridSize(kargs.M, kargs.N);
do
@@ -763,6 +764,7 @@ struct MoeFlatmmKernel
this->operator()(kargs, block_offset_m, block_offset_n);
partition_idx += gridDim.x;
} while(UsePersistentKernel && partition_idx < total_work_tile_cnt);
#endif
}
template <class MoeFlatmmKernelArgs>